Hadoop中的一些自定义
[*] 自定义计数器
计数器用来监控，hadoop中job的运行进度和状态。
如源文件内容为：
a b
c d e f
g h i
现在需要找出字段数大于3和小于3的记录条数，可以使用计数器来实现，代码如下：
public void map(LongWritable key, Text value,
OutputCollector output, Reporter reporter)
throws IOException {
String[] split = value.toString().split("\t");
if(split.length>3){
org.apache.hadoop.mapred.Counters.Counter counter = reporter.getCounter("MyCounter", "isLong");
counter.increment(1);
}else if(split.length
long> String name;
long age;
@Override
public void readFields(DataInput in) throws IOException {
this.id = in.readLong();
this.name = in.readUTF();
this.age = in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(id);
out.writeUTF(name);
out.writeLong(age);
}
@Override
public String toString() {
return "id:"+id+" name:"+name+" age:"+age;
}
public long getId() {
return> }
public String getName() {
return name;
}
public long getAge() {
return age;
}
}
代码二：基于key的比较
package cn.com.bonc.hadoop;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
public>
long> String name;
long age;
@Override
public void readFields(DataInput in) throws IOException {
in.readLong();
in.readUTF();
in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(id);
out.writeUTF(name);
out.writeLong(age);
}
@Override
public int compareTo(PersonSortByAge o) {
return (int) (this.id - o.id);
}
@Override
public String toString() {
return "id:"+id+" name:"+name+" age:"+age;
}
}
页:
[1]